cs571_Week_2_Lecture_questions_1

PART D and E only PLEASE!

Question 2: Answer the following questions. Show all the steps used to get to the final answer when applicable: C = Part A: What is C-¹? Part B: What is C × C-¹? 5 6 7 8 Part C: In 2-5 sentences explain the following: For neural networks why do we often build them with more than 1 neuron? Part D: In 2-5 sentences explain the following: In machine learning, why do we use two separate datasets for testing and training? Part E: In 2-5 sentences explain the following: Discuss one concept you found interesting or difficult to understand during our series of lectures on machine learning?

55

Represent the following knowledge using semantic net: "The Queen Mary is an ocean liner, and so is Swimming Pool. Every ocean liner is a ship. The oil tanker is a ship. Liverpool is an oil tanker. The engine and the hull are parts of the ship. The boiler is a part of the engine."

Question 17 Aa.Full explain this question and text typing work only     We should answer our question within 2 hours takes more time then we will reduce Rating Dont ignore this line

Based on whats shown in here, what is a simplified explanation as to what the summation symbol is exactly doing here and what does W and X represent, when this is being used in a neural network?

I need the answer as soon as possible

The difference between how and is one that a lot of people who are just starting out find difficult to understand.Could you offer an example to demonstrate the primary difference between "touch" and "cat"?

Please help with my artificial intelligence question below: Forward chaining and Backward chaining Suppose that the coding resulting from the acceptance of knowledge is as follows: A1 = body temperature >= 38°C A2 = cough A3 = cold A4 = persistent cough especially at night A5 = breath sounds P1 = common fever P2 = normal cough P3 = influenza / viral infection P4 = whooping cough P5 = respiratory tract infection The rules on the knowledge base include: R1 : IF A1 THEN P1 R2 : IF A2 THEN P2 R3 : IF P1 and (P2 or A3) THEN P3 R4 : IF P3 and A4 THEN P4 R5 : IF P3 and A5 THEN P5 The facts obtained from the user are that the fever, cough, and cough are more frequent at night (A1, A2, A4 → true). Explain the steps to get a conclusion if the inference technique used is: a. Forward chaining b. Backward chaining

Consider the (directed) network in the attached document We could represent this network with the following Prolog statements: link(a,b). link(a,c). link(b,c). link(b,d). link(c,d). link(d,e). link(d,f). link(e,f). link(f,g). Now, given this network, we say that there is a "connection" from a node "X" to a node "y" if we can get from "X" to "Y" via a series of links, for example, in this network, there is a connection from "a" to "d", and a connection from "c" to "f", etc.

Could you please share some instances to support your decision on the kind of machine learning to use?

Correct answer will be upvoted else Multiple Downvoted. Computer science. There is an endless 2-dimensional framework. The robot remains in cell (0,0) and needs to arrive at cell (x,y). Here is a rundown of potential orders the robot can execute:    move north from cell (i,j) to (i,j+1);    move east from cell (i,j) to (i+1,j);    move south from cell (i,j) to (i,j−1);    move west from cell (i,j) to (i−1,j);    stay in cell (i,j).    The robot needs to arrive at cell (x,y) in as couple of orders as could really be expected. In any case, he can't execute a similar order at least twice in succession.    What is the base number of orders needed to reach (x,y) from (0,0)?    Input    The main line contains a solitary integer t (1≤t≤100) — the number of testcases.    Every one of the following t lines contains two integers x and y (0≤x,y≤104) — the objective directions of the robot.    Output    For each testcase print a solitary integer — the base number of orders needed for the robot to…

Please design a neural network with one input layer, two hidden layers and one output layer. it has 2 inputs, 3 hidden neurons on each hidden layer, and one output neuron. please show your design logically, define an activation function for each neuron, and give a final output mathematical function. please make a method that can optimize weights. please write a perfect solution.

In artificial neural networks we use activation functions. Explain why you would select on activation function over another (for instance the sigmoidal function and tanh function)?

Express the following as semantic net with interconnected nodes and labelled arcs: Company ABC is a software development company. Three departments within the company are Sales, Administration and Programming. Joe is a manager of programming. Bill and Sue are programmer. Sue is married to Sam. Sam is editor of PHI. They have three children and they live on Elim street. Sue wears glasses and is 5.5 feet tall.

Neurons compute? The activation function and the linear function, which is represented by the equation z = Wx + b, are both calculated by neurons. Both a linear function, represented by the equation z = Wx + b, and an activation function are computed by neurons. When g is present in a neuron, the input x is scaled linearly (Wx + b). Before using the result in an activation function, neurons perform a calculation to get the mean of all of their features.

What is Reentrancy?

How many parameters in a neural network that has 2 hidden layers in which all layers are fully connected, an input example has 5 features, each hidden layer has 3 neurons, and the output layer has 1 neuron only? Draw the network and show your steps.

Correct answer will be upvoted else Multiple Downvoted. Computer science. The train framework can be addressed as directions on a 2D plane. The I-th train beginning at the base end is at first at (i,0) and will be at (i,T) after T minutes, and the I-th train beginning at the left end is at first at (0,i) and will be at (T,i) after T minutes. All trains show up at their objections following 101 minutes.    In any case, Gildong observed that a few trains booked to leave at a particular time, at the same time, are extremely hazardous. As of now, n trains are planned to leave from the base end and m trains are booked to withdraw from the left end. In the event that two trains are both at (x,y) simultaneously for some x and y, they will collide with one another. In this way, he is requesting you to observe the base number from trains that ought to be dropped to forestall every such accident.    Input    Each test contains at least one experiments. The main line contains the number of…

End Sub What is the result of below MatLab code. Provide the simulation steps in details. >>X-1:2:15 >> Y-7; >>For a-1 to Size (X) If X(a) > Y Y-X(a); End >> End >>Y I need a clear answer by hand, not by keyboard and fast answer within 20 minutes. Thank you | dybala

Submit solutions to the following problems in a single pdf document preferably completed using LaTeX. It is likely that you will need to use programming (Python) or a matrix calculator to solve most of the problems. You do not need to submit the code, but you should include explanations of all your conclusions. 1. Suppose a robot mouse is placed in a grid. Each room in the grid has doors that open to all other rooms. One room contains a trap so if the robot mouse enters that room, then the robot loses and the game ends. If the robot mouse makes it to the outside of the grid, then it wins and the game ends. Suppose the grid is 5x5 and the trap is in the third row, third column. When the robot mouse is placed in a room, it randomly selects a move left, right, up, or down until it is either trapped or reaches the outside. Assume that the starting point is never the room with the trap. What is the probability that the robot mouse will win the game? Does it depend on where the mouse begins?…

1 Question 1 A Deep Neural Network is shown in Figure 1. The aim of this network is to classify human and dog. 1. Calculate the initial error of the Deep Neural Network by feeding the following input: X₁ = 5, X₂ = 2. The X₁ indicates the length of the tail and X₂ indicates the number of eyes. 2. Update the layer 2 weights (ws,we,w7,ws) of the Deep Neural Network shown in Figure 1 for a single iteration. The learning rate is set to a = 1 and there are no biases in the neurons. 3. Recalculate the error with the updated weights of layer 2 and report its improvement with respect to the initial error (percentage wise). 4. (Bonus Question) Update and report the layer 1 weights (w₁,₂,3,w₁) of the network and estimate the improvement to the error.. Input X₁-5 X₂-2 W₂-0 W₂=0 w₂ = 0 W₁=0 Layer 1 3₁ W₁=0 ₂0 w₂0 Layer 2 Predicted Output Real Output 1 0 Figure 1: A Deep Neural Network designed for dog or human detection

Find two cases in the media (internet, TV, etc.) of a person (organization, etc.) attempting to describe and example of the process of Darwinian evolution but is incorrectly describing the evolution process using a Lamarckian approach to evolution. Give the following information for both cases: Source (Where you found it) In what ways are they mistakenly claiming that the evolutionary process is an example of Darwinian evolution? How do you know that they are really describing evolution through a Lamarckian process, not a Darwinian process?   Case 1:     Case 2:

Try to do asap if possible

How do I understand that I am getting the correct output when using the sigmoid function in a neural network? Considering that a sigmoid function (activation function) helps with checking the value between 0.00001 to 1.Also, what does it mean if you get output that are around 0.999877 or 0.999955 or within those values? Do these values represent how accurate the neural net is?

Consider the following procedure for initializing the parameters of a neural network: 1. Pick a random number r r = rand(1,1) * (2 + INIT_EPSILON ) – INIT_EPSILON 2. Set e =r for all i, j,l Does this work? No, because the procedure fails to break symmetry. O b. Yes, unless we are unlucky and get r = 0 (up to numerical precision). O. Yes or no, depending on the training set inputs x(i). d. Yes, because the parameters are chosen randomly.

For Artificial intelligence:

Supervised learning example: Iris classificationLet’s take a look at another example of this process, using the Iris dataset we discussed earlier. Our question will be this: given a model trained on a portion of the Iris data, how well can we predict the remaining labels?